With intelligent document processing (IDP), businesses can automate processes that include unstructured data. IDP is a broad technology category that includes intelligent intake, which enables companies to automate the processing of virtually any kind of content, including emails, for processes such as insurance claims and underwriting, customer onboarding, and mortgage processing. Intelligent intake automates the initial reading and categorization of documents as well as extraction of key data, dramatically reducing document intake time while improving accuracy.
At least 89% of AI projects fail to deliver, according to industry estimates.
But not with Indico: Our customers report a 94% success rate for production projects
Build high-quality custom machine learning models with as few as 200 labeled examples – a fraction of the data traditional AI solutions require
Accurately capture and validate real world data through an intuitive user interface and machine teaching
Realize faster time to market for new initiatives and improve customer satisfaction
As they embark on automation efforts, organizations often become frustrated by the limitations of robotic process automation (RPA), which generally works only with highly structured content.
Intelligent document processing has no such limitations. It not only enables businesses to automate processes that include unstructured data, such as document intake, but does so without the need for huge data sets normally required to accurately train automation models.
Instead, an intelligent document processing platform is based on a massive, pre-built database of labeled data points. The platform incorporates transfer learning, an artificial intelligence technology, which enables a model trained on one task to be used for a related task. Transfer learning obviates the need for a model to be trained on thousands of documents in order to achieve accuracy.
Indico Data, for example, has a base model consisting of some 500 million labeled data points. And thanks to transfer learning, it takes only about 200 documents and a few hours to train intelligent intake models to perform with about 95% accuracy. That reduces the underlying data required by a factor of 100 to 1000x as compared to traditional approaches.
That dramatic reduction in data required also means the Indico platform doesn’t require massive amounts of computing power, like many automated document processing technologies do. Rather, it can run effectively on just one or two GPUs, and scale from there using low-cost CPU.
IDP and intelligent intake have gained traction at financial institutions, insurance companies, commercial real estate firms and other companies that have reached the limit of what they can do with robotic process automation (RPA). These firms are looking to take the next step in their document processing automation journey when it comes to unstructured data.
While RPA and optical character recognition (OCR) templated approaches to document process automation work well with highly structured data, where the expected data is in the same place every time, RPA and OCR cannot handle unstructured data – such as email, Word documents, images, PDFs and more. It’s an important distinction because in most organizations, at least 80% of their data is unstructured, which first-generation automation solutions have difficulty dealing with.
It’s important to delve deeply into how each automated document processing solution for business works in order to understand its true capabilities. Today, many vendors are playing fast and loose with all kinds of AI-related terms, including IDP. You may come across RPA vendors who say they incorporate AI document processing technology to deliver what sounds like IDP. Under the covers, you will likely find the solution is merely a rules engine at heart that can’t handle unstructured data. In practice, “RPA + AI” solutions solve only for structured data, or, at best, semi-structured data, such as some invoices.
A true intelligent document processing solution needs to be able to incorporate document process automation that will handle any type of data: structured, semi-structured and unstructured. Given that the vast majority of data in your company is likely unstructured, only a solution that can effectively handle it will be able to accelerate your intelligent document automation processing and deliver transformative change. Don’t settle for less.
Indico’s intelligent document processing solution makes it easy to build models that automate document-intensive processes normally performed by humans.
Most processes require humans to read documents, find appropriate data and enter it into a downstream system. With Indico, the business subject matter experts who understand the processes best build intelligent intake models to automate such processes.
Using Indico’s intuitive tools, process experts label the data points they want to extract from documents. As they do so, the model updates in real time to show predictions on how well the model will perform the task at hand. When the prediction hits an acceptable level, you’re done. Typically, it takes a few dozen to maybe 200 documents to properly train a model.
Having the people who understand the business process and the desired results actually build the models is a crucial component of the Indico approach. It turns these business people into “citizen data scientists” – even though they don’t need any data science expertise. It’s a far more rapid and accurate approach than having business people try to explain a process to a data scientist, who then goes off and builds a model. With Indico, there’s no risk of requirements being lost in translation.
All Indico tools are in plain English and are simple to use. Fully working intelligent intake models can be built in as little as an hour.
While Indico’s platform is simple to use, it’s built on some sophisticated cognitive AI technology that we keep behind the scenes. That includes GPT, or Generative Pretrained Transformer models – the same technology behind ChatGPT.
Another example is deep learning. Normally, users have to program a model such that the computer can understand what it needs to do. Deep learning turns that notion around and says, “Show me examples of what you want to achieve and I’ll figure out how to do it.”
Natural language processing (NLP) is likewise a crucial element. NLP enables the Indico platform to understand context in a given piece of data– whether structured or unstructured. It enables the model to “read” a document and understand it just as a human would. But it functions strictly behind the scenes; there’s no need for business users to understand what NLP is or how it works.
That goes for machine learning (ML) as well. The Indico platform is built on sophisticated ML models, but users never have to interact with them. They simply focus on delivering business benefits by building models that remove repetition and complexity from document-intensive processes, while improving accuracy.
You may find other products that incorporate deep learning, NLP and ML to address processes that involve unstructured data, but you will likely find them to be far more complex to implement. Typically they do require data science expertise, along with millions of dollars to implement and maintain.
To create effective intelligent intake automation models on an enterprise scale, an IDP platform needs to support several key features, including:
As data passes through your production models, your process experts can offer corrections and selectively dictate which ones should be incorporated into the model.
Human in the loop is similar to staggered loop but can be configured such that any updated example employees submit is incorporated into the model, turning model updates into a highly-transparent, push-button process.
Whether for regulatory compliance or just peace of mind, you want to be able to explain how and why your automation models make decisions. Too often, AI engines make decisions in a black box, giving you no visibility into the rationale behind them.
Your automation platform should make it simple for anyone – from business process experts to auditors – to determine why a model made the decision it did.
You shouldn’t have to recreate the wheel when developing automation models. A sound intelligent document processing platform will give you access to hundreds of custom tasks, tens of billions of words, terabytes of images and bleeding-edge research that you can incorporate into your models. Access to open-source tools such as the Enso project is also a plus, providing a standard interface for the benchmarking transfer learning methods for natural language processing tasks.
Applying intelligent document processing to life insurance underwriting can help companies dramatically improve the process by largely taking humans out of the equation. With IDP and intelligent intake, companies can create models to quickly categorize and extract data from reams of documents.
The mortgage underwriting process typically involves humans looking over lots of documents to assess an applicant’s creditworthiness. The IDP platform applies intelligent intake to the processing of mortgage underwriting, “reading” the documents and extracting relevant data for input into the bank’s credit evaluation system.
Intelligent intake can “read” the various documents required to onboard a new customer and automatically classify them, extract relevant data and input it into the bank’s digital management system. Customers are onboarded more quickly, with increased accuracy, resulting in faster time to revenue for the bank and improved customer satisfaction.
Another common use case for commercial banking automation is meeting regulatory requirements around anti-money laundering (AML).In the U.S., that means complying with the Bank Secrecy Act and related regulations meant to deter money laundering by terrorist networks and drug cartels.
Closely related to AML requirements is “know your customer” regulations, and they present similar challenges. As part of the commercial banking client onboarding process, these laws require banks to make an effort to verify the identity of customers as well as the risks involved in any business relationship with them.
The LIBOR interest rate benchmark was phased out at the end of 2021. Banks and financial institutions worldwide are left poring through documents looking for references to LIBOR in order to determine what their exposure is and take steps to address it – a task that screams for IDP.
For insurance claims automation, intelligent document processing can classify and annotate new claims, and route them to the appropriate person for processing. It can also help extract pertinent information from documents, including unstructured data such as images and free-form notes from insurance adjusters.
Investment banking firms and others with wealth management divisions can take advantage of financial services automation by using it to analyze financial documents. Normally, humans read financial statements and pore over investment data, manually extracting relevant data. IDP enables financial firms to automate the process, pulling out relevant data and normalizing it for insertion into data processing tools. The result is a dramatic improvement in speed, efficiency and accuracy.
Investment firms often receive trade processing documents via email and in PDFs. They can use intelligent intake to automate trade processing by extracting relevant unstructured data from these documents, and normalize it for input into the firm’s digital management system, eliminating hours and hours of manual data processing.
While many consider invoices to be structured or semi-structured documents, given the variation in invoices from different companies, they really fall into the unstructured category. Nowhere is that more true than with respect to invoices from long-term healthcare facilities, where each provider uses its own format and lists numerous services provided. But customers are successfully using intelligent document processing to pull more than a dozen fields from these invoices and convert them to a structured format – a task no RPA or templated automation tool could handle.
Companies have long had the ability to transcribe call center conversations into text, but pulling out any actionable intelligence required employees to painstakingly read the transcripts. Intelligent document processing offers a way to automate call center transcript analysis. With its ability to “read” unstructured documents, an IDP model can be trained to analyze the text, looking for key words and phrases that indicate a caller may be amenable to buying additional goods or services, or is unhappy and in danger of jumping ship. Either way, that’s actionable intelligence that can deliver real business benefits.
Insurance is all about risk, and insurance companies are always looking for ways to reduce their own risk. Now some are getting creative, applying intelligent document processing to examine documents that may hold the keys to risk reduction. One company built an automation model to examine some 180,000 documents to find those that could help it more accurately price its workers’ compensation insurance policies. It took just one month to examine all the documents, a job that would’ve taken about 2.5 years for a single employee to accomplish. Others are using intelligent automation to increase accuracy in customer on-boarding, to reduce their risk of legal and regulatory mandate violations.
Use cases like those above make it easy to see how IDP and intelligent intake save companies time and money. From our experience with customers, here are the kind of gains you can expect from Indico:
Realize faster time to market for new initiatives and improve customer satisfaction
Create dramatic cost efficiencies for back-office functions and scale critical processes without increasing expenses
Free up employees from tedious, low-value tasks and repurpose them for higher value, more strategic projects
With no data science expertise required, turn your business process experts into citizen data scientists
Build effective models with a fraction of the data traditional artificial intelligence solutions require
Automate your most complex document-based workflows
The commercial real estate giant Cushman & Wakefield chose the Indico Unstructured Data Platform for intelligent document processing based on four differentiators:
A single automation initiative is saving Cushman & Wakefield at least 16,000 employee hours while also speeding turnaround time by 70%.
Read the full case study here.
As the largest independent financial risk management advisory and technology firm, Chatham Financial serves more than 3,000 companies and handles more than $750 billion in transaction volume annually.
After a thorough proof of concept (POC) project, Chatham chose Indico Data to help it automate the processing of tens of thousands of complex, unstructured documents. Among the results:
Read the full case study here.
When the global IT systems integrator and consulting firm Cognizant was searching for a solution to help a client automate processing unstructured mortgage title and deed documents, it turned to Indico Data. Cognizant helped the client achieve impressive results, including:
Read the full case study here.
A 150+ year-old Fortune 50 insurance company turned to Indico after it hit a wall with its robotic process automation (RPA) platform, which couldn’t process documents containing unstructured data. After a bakeoff, the company settled on Indico, in part on the strength of its intuitive user interface, which enabled “just about anybody” to build automation models.
The company’s “citizen data scientists” have created intelligent intake models to address use cases including:
“We’ve identified almost $100 million in hard value, hard dollar savings, that we can quite easily achieve over the next three to four years using unstructured data digitization and analytics tools,” said the company’s VP of Strategy and Planning.
Read the full case study here.
Perhaps figures like 85% reduction in cycle times and 4x increase in process capacity sound almost too good to be true. We can assure you they are most certainly real and add up to a rapid return-on-investment (ROI).
Consider a document-intensive process that involves 10 employees who each earn $100,000 per year, or $1 million total. Let’s say the team performs 500,000 tasks per year for a given process; that comes to $2 per task. If an IDP solution can automate 75% of those tasks – a perfectly reachable goal – the cost per task falls to just 50 cents, so the company saves $750,000 per year.
Looking at it another way, you now have $750,000-worth of employee hours to dedicate to other areas – a dramatic increase in overall capacity.
At the same time, by freeing up employees from tedious tasks, you gain soft benefits including increased employee satisfaction and productivity. Meanwhile, the IDP solution will perform the newly automated tasks with increased accuracy and consistency – because computers don’t get tired or make typos.